On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm

• URL: http://arxiv.org/abs/2402.00389v4
• Date: Fri, 07 Mar 2025 07:23:30 GMT
• Title: On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm
• Authors: Huan Li, Yiming Dong, Zhouchen Lin,
• Abstract summary: This paper considers the RMSProp and its momentum extension and establishes the convergence rate of $frac1Tsum_k=1T.<n>Our convergence rate matches the lower bound with respect to all the coefficients except the dimension $d$.<n>Our convergence rate can be considered to be analogous to the $frac1Tsum_k=1T.
• Score: 54.28350823319057
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension. This paper considers the classical RMSProp and its momentum extension and establishes the convergence rate of $\frac{1}{T}\sum_{k=1}^T E\left[\|\nabla f(x^k)\|_1\right]\leq O(\frac{\sqrt{d}C}{T^{1/4}})$ measured by $\ell_1$ norm without the bounded gradient assumption, where $d$ is the dimension of the optimization variable, $T$ is the iteration number, and $C$ is a constant identical to that appeared in the optimal convergence rate of SGD. Our convergence rate matches the lower bound with respect to all the coefficients except the dimension $d$. Since $\|x\|_2\ll\|x\|_1\leq\sqrt{d}\|x\|_2$ for problems with extremely large $d$, our convergence rate can be considered to be analogous to the $\frac{1}{T}\sum_{k=1}^T E\left[\|\nabla f(x^k)\|_2\right]\leq O(\frac{C}{T^{1/4}})$ rate of SGD in the ideal case of $\|\nabla f(x)\|_1=\varTheta(\sqrt{d}\|\nabla f(x)\|_2)$.

Related papers

• Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs [54.28273395444243]
  We show that the Monotonic Value Omega (MVP) algorithm achieves a variance-aware gap-dependent regret bound of $$tildeOleft(left(sum_Delta_h(s,a)>0 fracH2 log K land mathttVar_maxtextc$.
  arXiv  Detail & Related papers  (2025-06-06T20:33:57Z)
• On the $O(\rac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm [54.28350823319057]
  This paper establishes the convergence rate $frac1Ksum_k=1KEleft[|nabla f(xk)|_1right]leq O(fracsqrtdCK1/4) for AdamW measured by $ell_$ norm, where $K$ represents the iteration number, $d denotes the model dimension, and $C$ matches the constant in the optimal convergence rate of SGD.
  arXiv  Detail & Related papers  (2025-05-17T05:02:52Z)
• Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_0, L_1)$-Smoothness [74.18546828528298]
  We show that SignSGD with Majority Voting can robustly work on the whole range of complexity with $kappakappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappakappakappa-1right, kappa
  arXiv  Detail & Related papers  (2025-02-11T19:54:11Z)
• Improved convergence rate of kNN graph Laplacians [11.93971616098517]
  General class of $k$NN graph where the graph affinity is $W_ij = epsilon-d/2 . We prove the point-wise convergence of the $k$NN graph Laplacian to the limiting manifold operator.
  arXiv  Detail & Related papers  (2024-10-30T17:01:00Z)
• Measuring quantum relative entropy with finite-size effect [53.64687146666141]
  We study the estimation of relative entropy $D(rho|sigma)$ when $sigma$ is known. Our estimator attains the Cram'er-Rao type bound when the dimension $d$ is fixed.
  arXiv  Detail & Related papers  (2024-06-25T06:07:20Z)
• Convergence of a Normal Map-based Prox-SGD Method under the KL Inequality [0.0]
  We present a novel map-based algorithm ($mathsfnorMtext-mathsfSGD$) for $symbol$k$ convergence problems.
  arXiv  Detail & Related papers  (2023-05-10T01:12:11Z)
• Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning [77.22019100456595]
  We show a training algorithm for distributed computation workers with varying communication frequency. In this work, we obtain a tighter convergence rate of $mathcalO!!!(sigma2-2_avg!! . We also show that the heterogeneity term in rate is affected by the average delay within each worker.
  arXiv  Detail & Related papers  (2022-06-16T17:10:57Z)
• Faster Rates of Convergence to Stationary Points in Differentially Private Optimization [31.46358820048179]
  We study the problem of approximating stationary points of Lipschitz and smooth functions under $(varepsilon,delta)$-differential privacy (DP) A point $widehatw$ is called an $alpha$-stationary point of a function $mathbbRdrightarrowmathbbR$ if $|nabla F(widehatw)|leq alpha$. We provide a new efficient algorithm that finds an $tildeObig(big[
  arXiv  Detail & Related papers  (2022-06-02T02:43:44Z)
• The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning [3.8098187557917464]
  The paper concerns the $d$-dimensional recursion approximation, $$theta_n+1= theta_n + alpha_n + 1 f(theta_n, Phi_n+1) The main results are established under additional conditions on the mean flow and a version of the Donsker-Varadhan Lyapunov drift condition known as (DV3) An example is given where $f$ and $barf$ are linear in $theta$, and $Phi$ is a geometrical
  arXiv  Detail & Related papers  (2021-10-27T13:38:25Z)
• Nearly Horizon-Free Offline Reinforcement Learning [97.36751930393245]
  We revisit offline reinforcement learning on episodic time-homogeneous Markov Decision Processes with $S$ states, $A$ actions and planning horizon $H$. We obtain the first set of nearly $H$-free sample complexity bounds for evaluation and planning using the empirical MDPs.
  arXiv  Detail & Related papers  (2021-03-25T18:52:17Z)
• Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions [20.666734673282498]
  The (1+1)-evolution strategy (ES) with success-based step-size adaptation is analyzed on a general convex quadratic function. The convergence rate of the (1+1)-ES is derived explicitly and rigorously on a general convex quadratic function.
  arXiv  Detail & Related papers  (2021-03-02T09:03:44Z)
• Private Stochastic Convex Optimization: Optimal Rates in $\ell_1$ Geometry [69.24618367447101]
  Up to logarithmic factors the optimal excess population loss of any $(varepsilon,delta)$-differently private is $sqrtlog(d)/n + sqrtd/varepsilon n.$ We show that when the loss functions satisfy additional smoothness assumptions, the excess loss is upper bounded (up to logarithmic factors) by $sqrtlog(d)/n + (log(d)/varepsilon n)2/3.
  arXiv  Detail & Related papers  (2021-03-02T06:53:44Z)
• Accelerating Optimization and Reinforcement Learning with Quasi-Stochastic Approximation [2.294014185517203]
  This paper sets out to extend convergence theory to quasi-stochastic approximations. It is illustrated with applications to gradient-free optimization and policy gradient algorithms for reinforcement learning.
  arXiv  Detail & Related papers  (2020-09-30T04:44:45Z)
• A Simple Convergence Proof of Adam and Adagrad [74.24716715922759]
  We show a proof of convergence between the Adam Adagrad and $O(d(N)/st)$ algorithms. Adam converges with the same convergence $O(d(N)/st)$ when used with the default parameters.
  arXiv  Detail & Related papers  (2020-03-05T01:56:17Z)
• Closing the convergence gap of SGD without replacement [9.109788577327503]
  gradient descent without replacement sampling is widely used in practice for model training. We show that SGD without replacement achieves a rate of $mathcalOleft(frac1T2+fracn2T3right)$ when the sum of the functions is a quadratic.
  arXiv  Detail & Related papers  (2020-02-24T17:37:28Z)
• Revisiting EXTRA for Smooth Distributed Optimization [70.65867695317633]
  We give a sharp complexity analysis for EXTRA with the improved $Oleft(left(fracLmu+frac11-sigma_2(W)right)logfrac1epsilon (1-sigma_2(W))right)$. Our communication complexities of the accelerated EXTRA are only worse by the factors of $left(logfracLmu (1-sigma_2(W))right)$ and $left(logfrac1epsilon (1-
  arXiv  Detail & Related papers  (2020-02-24T08:07:08Z)
• Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness [151.67113334248464]
  We show that extending the smoothing technique to defend against other attack models can be challenging. We present experimental results on CIFAR to validate our theory.
  arXiv  Detail & Related papers  (2020-02-08T22:02:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.